The Design and Analysis of Stochastic Cost-Effectiveness Studies for the Evaluation of Health Care Interventions
- PDF / 841,039 Bytes
- 14 Pages / 504 x 720 pts Page_size
- 46 Downloads / 166 Views
Drug Information Journal. Vol.
0092-8615/2001 Copyright 0 2001 Drug Information Association Inc.
THE DESIGN AND ANALYSIS OF STOCHASTIC COST-EFFECTIVENESS STUDIES FOR THE EVALUATION OF HEALTH CARE INTERVENTIONS ANDREW
BRIGGS
Health Economics Research Centre, Institute of Health Sciences, University of Oxford, Oxford, England
MAGNUSTAMBOUR Centre for Health Economics, Department of Economics, Stockholm School of Economics, Stockholm, Sweden
Many clinical trials are in progress that involve the collection of patient-level data on both the health outcome and resource use consequences of the health care interventions under evaluation. The overall aim of many such evaluations will be to undertake a costeffectiveness analysis, which will often result in a cost-effectiveness ratio summarizing the value for money of the intervention in question. In this papel; we explore the issues surrounding the design and analysis of such studies. At the design stage of an analysis, we propose an improved sample size formula for cost-effectiveness analysis that allows for covariance between cost and effect differences. This approach is based on the 0; dominance-accept
new treatment as it is both cheaper and more effective than the existing therapy, 2. pn - pCc> 0; pm- pEC< 0; dominance-reject new treatment as it is both more expensive and less effective than the existing therapy, 3. pCr- pCc> 0; pL7- pLEC > 0; trade-of-consider the magnitude of the additional cost of the new therapy relative to its additional effectiveness, and 4. pcr- pCc< 0; par- pEc< 0; trade-of-consider the magnitude of the cost-saving of the new therapy relative to its reduced effectiveness. These four situations correspond to the four quadrants of the cost-effectiveness (CE) plane, which has been proposed for presenting cost-effectiveness results (9,lO). The CE plane is presented in Figure 1. Where one intervention is simultaneously cheaper and more effective than the other (Situations 1 and 2 above and the southeast (SE) and northwest (NW) quadrants on the CE plane) it is clearly the treatment of choice since it dominates the alternative intervention. However, where one intervention is both more effective and more costly (Situations 3 and 4 above and the northeast (NE)and southwest (SW) quadrants on the cost-effectiveness plane) then the decision is no longer clear. Rather, a judgment must be made concerning whether the difference in effectiveness resulting from a switch in therapy is justified given the difference in costs that such a switch would bring about. In order to aid such judgment, an incremental cost-effectiveness ratio (ICER) should be calculated that provides a summary of the cost-effectiveness of one intervention relative to the other: ICER = Pcr - Pcc Pm - P E C
In the absence of the simple case of dominance, the decision over which is the appropriate treatment to implement cannot be determined unless a cut-off value, or maximum willingness
Stochastic Cost-Effectiveness Studies for Health Care Interventions
1457
FIGURE 1. Decision rules an
Data Loading...
